Human behaviour recognition

This project aims to explore different methodologies in action recognition, including state-of-the-art techniques. The report presents the findings of the survey on video action recognition models and datasets, as well as the latest advancements in action recognition models and large-scale multi-vie...

Full description

Saved in:
Bibliographic Details
Main Author: Ng, Cheryl Si Ying
Other Authors: Tan Yap Peng
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/167656
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:This project aims to explore different methodologies in action recognition, including state-of-the-art techniques. The report presents the findings of the survey on video action recognition models and datasets, as well as the latest advancements in action recognition models and large-scale multi-view datasets. Additionally, the report also discusses the application of transfer learning, which is a machine learning technique that uses the knowledge gained from one domain to improve the performance of a model in another domain.